CBSE Class 10 · Artificial Intelligence · board exam 2027
Chapter 2: Advanced Concepts of Modeling in AI — notes
The chapter’s 8 parts in the book’s order — the first idea of each and the points Medha Ma’am writes on the board — and the summary at the end. The full lesson and a check question for each part are in the app.
1. AI, ML and DL
Okay, so, you must have heard three words a lot — AI, ML and DL.
- • AI: computers mimic human intelligence
- • ML: machines improve with experience
- • DL: software trains itself on vast data
- • AI > ML > DL (funnel / umbrella)
- • ML example: apple vs strawberry
- • DL example: bird image pixels -> 'bird'
2. Data, features and labels
Okay, so let's talk about data.
- • Features = columns of the table
- • Label = the special feature we predict
- • Colour -> feature; fruit name -> label
- • Labeled data: tag attached
- • Unlabeled data: raw, no tag
- • Training set teaches; testing set checks accuracy
3. Rule based and learning based models
Okay, so — modelling means building algorithms, we call them models, that can be trained to give smart outputs.
- • Rule based: developer defines the rules
- • Example: order-tracking chatbot
- • Drawback: learning is static
- • Learning based: machine learns by itself
- • Adapts to changes in data
- • Example: spam email filter
4. Supervised learning
Machine learning can be divided into three parts: supervised, unsupervised and reinforcement learning.
- • Supervised = learning from labeled data
- • Coins: Euro 5 g, Dirham 7 g, Dollar 3 g, Rupee 4 g
- • Feature: weight; Label: currency
- • Classification: discrete (spam / not spam)
- • Regression: continuous (house price)
5. Unsupervised learning
Okay, so let's talk about unsupervised learning.
- • Unsupervised = unlabeled data, no guidance
- • Finds patterns, similarities and differences
- • Clustering: groups similar objects
- • e.g. animals in cluster 1, birds in cluster 2
- • Association: bread -> butter
6. Reinforcement learning
Okay, so let's talk about reinforcement learning.
- • Learn by rewarding actions
- • Trial and error
- • 'cherry' -> negative feedback
- • 'apple' -> positive feedback
- • Examples: parking a car, humanoid walking
7. Neural networks
Okay, so let's talk about neural networks.
- • Modelled on neurons in the human brain
- • Input layer: takes data, no processing
- • Hidden layers: compute with weights and biases
- • Output layer: gives result, no processing
- • Weights adjusted using the error
8. How AI makes a decision
Okay, so let's see how a perceptron makes a decision — like whether to go to the park.
- • Inputs X1 to X4, weights, bias B with WB
- • Yes = 1, No = 0, bias = 1
- • Sum it all up, compare with threshold 0
- • Inputs 1, 0, 1, 0 -> output 0.5 -> go out
- • Output -0.5 -> do not go out
Summary
Okay, so let's go back over everything we covered today. First, you saw that AI is the big umbrella term. Machine Learning sits under AI, and Deep Learning sits under Machine Learning. Then we talked about data — it has features and labels. Training data teaches a model, and testing data checks how accurate it is. Next, you compared two kinds of models. Rule based models — their learning stays fixed, it's static. Learning based models, though, adapt when things change. You then met three kinds of machine learning. Supervised learning, which covers classification and regression, uses labeled data. Unsupervised learning, which covers clustering and association, finds patterns in data that has no labels. And reinforcement learning — that one learns through rewards. Finally, you saw how a neural network passes data through its layers — input, hidden, and output. And a perceptron, remember, adds up weighted inputs and compares that total with a threshold, to decide what to do. That's a lot we've covered — so tell me, out of all these, which idea felt the most new to you?
AskMedha · Medha Ma’am — CBSE Class 10 Artificial Intelligence, Chapter 2. Written from the textbook, checked twice.
Questions parents and students ask
- How do I get the "Advanced Concepts of Modeling in AI" notes as a PDF?
- Press "Save as PDF" — the phone’s print sheet opens; choose "Save as PDF" there. The PDF holds the notes only.
- Where are these notes written from?
- From the chapter’s own textbook text, part by part, in the book’s own terms; a second, independent model then checked every part against the book. The full lesson, a check question for each part and the practice are in the AskMedha app.
The same preparation, with Medha Ma’am — on your phone
Every question of every chapter with its model answer, practice questions in the board’s own shapes, 60 minutes of class a day, written answers marked, a test every Sunday and a WhatsApp report to parents.
Medha Ma’am is an AI teacher, not a live tutor. Every answer is checked twice; a person takes responsibility.